We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent ec25d6c commit 4680f60Copy full SHA for 4680f60
examples/3 - Neural Networks/recurrent_network.py
@@ -15,6 +15,11 @@
15
from tensorflow.models.rnn import rnn, rnn_cell
16
import numpy as np
17
18
+'''
19
+To classify images using a reccurent neural network, we consider every image row as a sequence of pixels.
20
+Because MNIST image shape is 28*28px, we will then handle 28 sequences of 28 steps for every sample.
21
22
+
23
# Parameters
24
learning_rate = 0.001
25
training_iters = 100000
0 commit comments